| { |
| "best_metric": 0.8813333333333333, |
| "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0931/checkpoints/checkpoint-999", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 999, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 33.17395782470703, |
| "learning_rate": 0.00019999999999999998, |
| "loss": 1.6167, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8456, |
| "eval_loss": 0.5034552216529846, |
| "eval_runtime": 12.4066, |
| "eval_samples_per_second": 302.257, |
| "eval_steps_per_second": 4.756, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 57.69203186035156, |
| "learning_rate": 9.999999999999999e-05, |
| "loss": 0.4175, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8656, |
| "eval_loss": 0.41481438279151917, |
| "eval_runtime": 12.2511, |
| "eval_samples_per_second": 306.094, |
| "eval_steps_per_second": 4.816, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 59.077388763427734, |
| "learning_rate": 0.0, |
| "loss": 0.2146, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8813333333333333, |
| "eval_loss": 0.38468724489212036, |
| "eval_runtime": 12.6433, |
| "eval_samples_per_second": 296.6, |
| "eval_steps_per_second": 4.667, |
| "step": 999 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 999, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.4529287718656e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
